Hi All,
I am using the package 'penalized' to perform a multiple regression on a
dataset of 33 samples and 9 explanatory variables. The analysis appears to
have performed as outlined and I have ended up with 4 explanatory variables
and their respective regression coefficients. What I am struggling to
understand is where do I get the variance explained information from and how
do I determine the relative importance of the 4 variables selected? It does
not appear to be a part of the penalized procedure.
I submit the final call to 'penalized' with the estimated values of lambda1
and lambda2
> fitfinal <-
penalized(CHAB~.,data=chabun,lambda1=356.0856,lambda2=3.458605,model =
"linear",steps=1,standardize = TRUE)
# nonzero coefficients: 5
> fitfinal
Penalized linear regression object
10 regression coefficients of which 5 are non-zero
Loglikelihood = -154.1055
L1 penalty = 4944.889 at lambda1 = 356.0856
L2 penalty = 234.7781 at lambda2 = 3.458605
> coefficients (fitfinal)
(Intercept) BC POC EXP FI
4.685739e+01 2.074521e-01 1.079459e-01 -1.373058e-05 -2.295339e+00
cheers
Andy
--
Andrew Halford Ph.D
Associate Research Scientist
Marine Laboratory
University of Guam
Ph: +1 671 734 2948
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
